Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3766 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0373. Min Act: -0.0000

Data Index: 1836528 (The Pile)

Max Activating Token Index: 58

Text #1

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0344. Min Act: -0.0000

Data Index: 810520 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1112220 (The Pile)

Max Activating Token Index: 222

Text #3

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1852785 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0335. Min Act: -0.0000

Data Index: 567094 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0336. Min Act: -0.0000

Data Index: 812868 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0328. Min Act: -0.0000

Data Index: 369190 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0326. Min Act: -0.0000

Data Index: 182550 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0324. Min Act: -0.0000

Data Index: 1071017 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0323. Min Act: -0.0000

Data Index: 869853 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1463441 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1261617 (The Pile)

Max Activating Token Index: 171

Text #12

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1814723 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0312. Min Act: -0.0000

Data Index: 736301 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0321. Min Act: -0.0000

Data Index: 918197 (The Pile)

Max Activating Token Index: 232

Text #15

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0306. Min Act: -0.0000

Data Index: 257959 (The Pile)

Max Activating Token Index: 143

Text #16

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0304. Min Act: -0.0000

Data Index: 957102 (The Pile)

Max Activating Token Index: 191

Text #17

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0298. Min Act: -0.0000

Data Index: 617838 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0297. Min Act: -0.0000

Data Index: 748714 (The Pile)

Max Activating Token Index: 96

Text #19

Max Range: 0.0373. Min Range: -0.0373

Max Act: 0.0297. Min Act: -0.0000

Data Index: 892460 (The Pile)

Max Activating Token Index: 85